Open AccessDeep Learning-based Facial Expression Recognition and Analysis for Filipino Gamers
Author(s) -
Juan Raphael Sena,
Melvin K. Cabatuan
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.b1027.078219
Subject(s) - categorical variable , computer science , artificial intelligence , facial expression recognition , facial expression , facial recognition system , empathy , deep learning , emotion recognition , test (biology) , face (sociological concept) , test data , machine learning , speech recognition , pattern recognition (psychology) , psychology , paleontology , biology , social science , psychiatry , sociology , programming language
This paper presents a computer vision based emotion recognition system for the identification of six basic emotions among Filipino Gamers using deep learning techniques. In particular, the proposed system utilized deep learning through the Inception Network and Long-Short Term Memory (LSTM). The researchers gathered a database for Filipino Facial Expressions consisting of 74 gamers for the training data and 4 gamer subjects for the testing data. The system was able to produce a maximum categorical validation accuracy of .9983 and a test accuracy of .9940 for the six basic emotions using the Filipino database. The cross-database analysis results using the well-known Cohn -Kanade+ database showed that the proposed Inception-LSTM system has accuracy on a par with the current existing systems. The results demonstrated the feasibility of the proposed system and showed sample computations of empathy and engagement based on the six basic emotions as a proof of concept